Image-based temporal profiling of autophagy-related phenotypes

Abstract

AbstractAutophagy is a dynamic process that is critical in maintaining cellular homeostasis. Dysregulation of autophagy is linked to many diseases and is emerging as a promising therapeutic target. High-throughput methods to characterize autophagy are essential for accelerating drug discovery and characterizing mechanisms of action. In this study, we developed a highly scalable image-based profiling approach to characterize ∼900 morphological features at a single cell level with high temporal resolution. We differentiated drug treatments based on morphological profiles using a random forest classifier with ∼90% accuracy and identified the key features that govern the classification. Additionally, temporal morphological profiles accurately predicted biologically relevant changes in autophagy after perturbation, such as total cargo degradation. Therefore, this study acts as proof-of-principle for using image-based profiling to differentiate autophagy perturbations in a high-throughput manner and identify biologically relevant autophagy phenotypes, which can accelerate drug discovery.